specific method Β· filed under inference & serving
Four-Over-Six
Four-Over-Six is an FP4 weight scale-selection rule for post-training quantization that sets the per-block NVFP4 weight scale.1,2 For each weight microblock it chooses between the M = 4 and M = 6 FP4 grids, picking whichever option minimizes reconstruction error.3
Trade-off It trades a small amount of additional zero-rounding for better handling of high-magnitude tails.4
How this definition was written
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
Four-Over-Six (Cook et al.) scaling
β NVIDIA Nemotron 3 Ultra Technical ReportEach algorithm changes the per-block NVFP4 scale
β NVIDIA Nemotron 3 Ultra Technical ReportFour-Over-Six selects between theπ = 4and π = 6weight grids per block, using the option that minimizes
β NVIDIA Nemotron 3 Ultra Technical ReportThis trades a small amount of additional zero-rounding for better handling of high-magnitude tails
β NVIDIA Nemotron 3 Ultra Technical Report
Also called Four-Over-Six FP4 weight scale selection, Four-Over-Six scale selection method, Four-Over-Six weight scaling.